}

    /**
     * Field name for session ID.
     */
    public static final String SESSION_ID = "sessionId";

    /**
     * Field name for filter type.
     */
    public static final String FILTER_TYPE = "filterType";

    /**
     * Field name for URL.
     */
    public static final String URL = "url";

    /**
     * The unique identifier for this URL filter.
     */
    private String id;

    protected long delayMillisAtNoUrlInQueue = 500L;

    /** Delay in milliseconds before processing a URL */
    protected long delayMillisBeforeProcessing = 0L;

    /** Delay in milliseconds for waiting for new URLs */
    protected long delayMillisForWaitingNewUrl = 1000L;

    /**
     * Default constructor with default delay values.
     */
    public DefaultIntervalController() {
    }

    /**

import jakarta.annotation.Resource;

/**
 * Abstract base class for implementing {@link Rule} interfaces.
 * Provides common functionality and properties for crawler rules.
 *
 * <p>
 * This class handles the registration of rules with the {@link RuleManager}
 * and provides getter and setter methods for common properties such as
 * {@code ruleId} and {@code responseProcessor}.
 * </p>
 *
 * <p>

    /** The encoding for the output. */
    protected String outputEncoding = Constants.UTF_8;

    /** The extension for the output file. */
    protected String outputExtension = null;

    /** The temporary directory for input/output files. */
    protected File tempDir = null;

    /** The command to execute. */
    protected String command;

    /** The timeout for command execution in milliseconds. */

 *
 * @author shinsuke
 *
 */
public class OpenSearchUrlQueueService extends AbstractCrawlerService implements UrlQueueService<OpenSearchUrlQueue> {
    /**
     * Logger instance.
     */
    private static final Logger logger = LogManager.getLogger(OpenSearchUrlQueueService.class);

    /**
     * Data service for checking access results.
     */
    @Resource

                        }
                    }
                }
            });
        }

        // Start all threads
        for (Thread thread : threads) {
            thread.start();
        }

        // Wait for all threads to complete
        for (Thread thread : threads) {
            thread.join();
        }

        // Verify results
        assertTrue(exceptions.isEmpty());

        // NOP
    }

    /**
     * Field name for ID.
     */
    public static final String ID = "id";

    /**
     * Field name for session ID.
     */
    public static final String SESSION_ID = "sessionId";

    /**
     * Field name for method.
     */
    public static final String METHOD = "method";

    /**
     * Field name for URL.
     */
    public static final String URL = "url";

import org.xml.sax.InputSource;

/**
 * Extracts text content from HTML documents.
 */
public class HtmlExtractor extends AbstractXmlExtractor {
    /** Logger for this class. */
    protected static final Logger logger = LogManager.getLogger(HtmlExtractor.class);

    /** Pattern for extracting charset from meta tags. */
    protected Pattern metaCharsetPattern = Pattern.compile("<meta.*content\\s*=\\s*['\"].*;\\s*charset=([\\w\\d\\-_]*)['\"]\\s*/?>",

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.exception;

/**
 * The class CrawlerSystemException is a runtime exception that is thrown when a system error occurs during crawling.
 * It extends the RuntimeException class and provides constructors for creating exceptions with a message, a cause, or both.

            Pattern.MULTILINE | Pattern.CASE_INSENSITIVE);

    /**
     * Map of features for the DOM parser.
     */
    protected Map<String, String> featureMap = new HashMap<>();

    /** Map of properties for the DOM parser. */
    protected Map<String, String> propertyMap = new HashMap<>();

    /** XPath expression to select target nodes for text extraction. */
    protected String targetNodePath = "//HTML/BODY | //@alt | //@title";